CN108108457A - Method, storage medium and the terminal of big beat information are extracted from music beat point - Google Patents
Method, storage medium and the terminal of big beat information are extracted from music beat point Download PDFInfo
- Publication number
- CN108108457A CN108108457A CN201711466076.3A CN201711466076A CN108108457A CN 108108457 A CN108108457 A CN 108108457A CN 201711466076 A CN201711466076 A CN 201711466076A CN 108108457 A CN108108457 A CN 108108457A
- Authority
- CN
- China
- Prior art keywords
- beat
- point
- big
- cycle
- beat point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000001514 detection method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 239000011324 bead Substances 0.000 claims description 2
- 238000000605 extraction Methods 0.000 abstract description 10
- 230000033764 rhythmic process Effects 0.000 description 18
- 230000006854 communication Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 9
- 230000008451 emotion Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 239000013589 supplement Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012905 input function Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009527 percussion Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000001020 rhythmical effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 241000288673 Chiroptera Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H1/00—Details of electrophonic musical instruments
- G10H1/0008—Associated control or indicating means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
- G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
- G10H2210/076—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for extraction of timing, tempo; Beat detection
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Acoustics & Sound (AREA)
- Electrophonic Musical Instruments (AREA)
- Auxiliary Devices For Music (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides method, storage medium and the terminal that big beat information is extracted in a kind of point from music beat, and applied to multimedia information technique field, wherein method includes step:According to each beat point of the music of input, several candidates beat cycle is obtained;Several beat point sequences in each candidate's beat cycle are generated, and calculate the weight of each beat point sequence, wherein, two neighboring beat point is using corresponding candidate's beat cycle as interval in the beat point sequence;The beat point sequence of weight selection maximum from several beat point sequences in each candidate's beat cycle, the maximum weights sequence as each candidate's beat cycle;According to the maximum weights sequence in each candidate's beat cycle and corresponding weight, big beat information is obtained.The embodiment of the present invention realizes the extraction of big beat information.
Description
Technical field
The present invention relates to multimedia information technique fields, specifically, are carried the present invention relates to one kind from music beat point
Take method, storage medium and the terminal of big beat information.
Background technology
Music beat point is that frame drum percussion in music, piano stress, voice climax etc. possess stronger rhythmic appearance
Time point general designation.And big beat (Big Beat) is to be sent out for mid-term in one kind that Britain rises based on electronics dance music nineteen ninety
It opens up and come the musical form gone up.Typically, in order to which music is allowed to have better sense of auditory rhythm, melody producer can be in music
The big beat point of one group of cycle (or paracycle) is added in beat point.Exemplified by having the music that frame drum participates in performance, usually make
It is roused to play this group of beat point with the army in frame drum, therefore is otherwise known as " army's drumbeat ".Since big bar and rhythm sense is more preferable,
Therefore big beat information is extracted from music beat point, to be applied in the required each scene of user, possesses important meaning
Justice.And do not occur the scheme for accordingly extracting big beat information in traditional technology also.
The content of the invention
The present invention is directed to the shortcomings that existing way, propose to extract in a kind of point from music beat the method for big beat information,
Storage medium and terminal, to solve in the prior art to extract asking for big beat information from music beat point
Topic extracts big beat information to realize from music beat point.
The embodiment of the present invention provides in a kind of point from music beat according to the first aspect and extracts big beat information
Method, including step:
According to each beat point of the music of input, several candidates beat cycle is obtained;
Several beat point sequences in each candidate's beat cycle are generated, and calculate the weight of each beat point sequence,
In, two neighboring beat point is using corresponding candidate's beat cycle as interval in the beat point sequence;
The beat point sequence of weight selection maximum from several beat point sequences in each candidate's beat cycle, as every
The maximum weights sequence in a candidate's beat cycle;
According to the maximum weights sequence in each candidate's beat cycle and corresponding weight, big beat information is obtained.
The method that big beat information is extracted in the point provided in this embodiment from music beat, according to each beat point of input
Several candidates beat cycle is obtained, the maximum weights sequence in each candidate's beat cycle is then obtained, according to maximum weights sequence
Row and corresponding weight can get big beat information automatically, it is achieved thereby that the extraction of big beat information.
In one embodiment, each beat point of the music according to input, obtains several candidates beat cycle,
Including:
Record the time interval between every two neighboring beat point in all beat points of input;
The statistics with histogram of Gaussian Profile is carried out to each time interval, obtains histogram, wherein, the horizontal stroke of the histogram
For coordinate for characterizing time interval, ordinate is used to characterize the number of time interval appearance;
Peak detection is carried out to the histogram, obtains several peak points;
The peak point of the order selection preset number of number from big to small is corresponded to according to peak point, by the peak value of preset number
Point corresponding interval time is as candidate's beat cycle.
The present embodiment carries out statistics with histogram using the mode of Gaussian Profile, and system is ensure that while eliminating error and influencing
The precision of result is counted, so as to obtain more accurate big beat information.
In one embodiment, the statistics with histogram that Gaussian Profile is carried out to each time interval, including:
Build initial histogram;
A time interval is chosen from all time intervals as current time interval;
The numerical value of current time interval position described in the initial histogram is increased into N, and will be described initial
Own in histogram | t-T | the numerical value at the position of < δ increases Wherein, T is the current time
Interval, t are the time interval in addition to the current time interval, and δ is predetermined threshold value;
Another time interval is chosen from all time intervals as current time interval, is returned the initial histogram
The numerical value of current time interval position described in figure increases N, and will own in the initial histogram | t-T | < δ's
Numerical value at position increasesThe step of, until all time intervals are selected as current
Time interval.
In one embodiment, the beat point includes strong beat point and weak beat point;
The weight for calculating each beat point sequence, including:
A beat point sequence is chosen from all beat point sequences as current beat point sequence;
Sequentially obtain two adjacent beat points in the current beat point sequence;
If two adjacent beat points are strong beat point in the current beat point sequence, by the current beat point sequence
The weight of row adds the first setting value;
If in the current beat point sequence in two adjacent beat points one for strong beat point another be weak beat
Point, by the weight of the current beat point sequence plus the second setting value, wherein, second setting value is set less than described first
Definite value;
If two adjacent beat points are weak beat point in the current beat point sequence, by the current beat point sequence
The weight of row adds the 3rd setting value, wherein, the 3rd setting value is less than second setting value;
It, will if the interval of two adjacent beat points is more than corresponding candidate's beat cycle in the current beat point sequence
The weight of the current beat point sequence reduces the 4th setting value;
The weight obtained all over the adjacent beat point of each two in the current beat point sequence will be gone through, with corresponding candidate's beat
The evolution in cycle is multiplied, and obtains the final weight of the current beat point sequence;
Another beat point sequence is chosen from all beat point sequences as current beat point sequence, return sequentially obtains
In the current beat point sequence the step of two adjacent beat points, until all beat point sequences be selected as work as
Preceding beat point sequence.
The present embodiment calculates the weight of each beat point sequence by the weight calculation mode of design, so as to effective
Reduction common 1/2,1/3,2 times big beat cycle interference, obtain correctly big beat information.
In one embodiment, several beat point sequences in generation each candidate's beat cycle, including:
Candidate's beat cycle is chosen from all candidate's beat cycles as the current beat cycle;
A beat point is chosen from all beat points of input as starting beat point;
The interval found from the beat point behind the starting beat point between the starting beat point meets isoperimetric
The beat point of phase spaced apart condition, wherein, the isoperimetric phase spaced apart condition includes the interval and the positive integer in current beat cycle
Error between times is in setting range;
A beat point in the current beat cycle is made of the starting beat point and all beat points searched out
Sequence;
Another beat point is chosen from all beat points of input as starting beat point, is returned from the starting beat
The step that the interval between the starting beat point meets the beat point of isoperimetric phase spaced apart condition is found in the beat point of point below
Suddenly, until all beat points are selected as starting beat point;
Another candidate's beat cycle is chosen from all candidate's beat cycles as the current beat cycle, is returned from input
All beat points in choose the step of beat point is as starting beat point, until all candidate's beat cycles are selected
As the current beat cycle.
In one embodiment, the big beat information includes big beat cycle and big beat point;
The maximum weights sequence and corresponding weight in basis each candidate's beat cycle, obtain big beat information,
Including:
Candidate's beat cycle of weight maximum is selected from all candidate's beat cycles, candidate's beat cycle of selection is made
For the big beat cycle, using each beat point in the maximum weights sequence in the candidate's beat cycle selected as big beat point.
In one embodiment, described each beat point by the maximum weights sequence in candidate's beat cycle of selection
After big beat point, further include:
If in other beat points in all beat points of input in addition to as big beat point, there are beat points and any one
The positive integer times at intervals of the big beat cycle between a big beat point, and the big beat cycle of the interval no more than 2 times, will
The beat point is determined as big beat point.
The big beat point that the present embodiment is omitted by decision condition supplement further improves the accurate of big beat point extraction
Property.
In one embodiment, described each beat point by the maximum weights sequence in candidate's beat cycle of selection
After big beat point, further include:
If in other beat points in all beat points of input in addition to as big beat point, there are two beat points with appointing
Interval between what one big beat point is the positive integer times in big beat cycle, and between two beat points at intervals of big
Two beat points are determined as big beat point by the beat cycle.
The big beat point that the present embodiment is omitted by decision condition supplement further improves the accurate of big beat point extraction
Property.
The embodiment of the present invention additionally provides a kind of computer readable storage medium, stores thereon according to the second aspect
There is computer program, which realizes when being executed by processor extracts big section in the slave music beat point described in foregoing any one
The method for clapping information.
Computer readable storage medium provided in this embodiment obtains several candidates section according to each beat point of input
The cycle is clapped, then obtains the maximum weights sequence in each candidate's beat cycle, according to maximum weights sequence and corresponding weight just
Big beat information can be got automatically, it is achieved thereby that the extraction of big beat information.
The embodiment of the present invention additionally provides a kind of terminal, the terminal includes according to the 3rd aspect:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes the method that big beat information is extracted in the slave music beat point described in foregoing any one.
Terminal provided in this embodiment obtains several candidates beat cycle according to each beat point of input, then obtains
The maximum weights sequence in each candidate's beat cycle is taken, can be got automatically according to maximum weights sequence and corresponding weight
Big beat information, it is achieved thereby that the extraction of big beat information.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
It obtains substantially or is recognized by the practice of the present invention.
Description of the drawings
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein:
Fig. 1 is the flow signal for the method that big beat information is extracted in the slave music beat point of one embodiment of the invention
Figure;
Fig. 2 is the schematic diagram of the big beat information application scenarios of a specific embodiment of the invention;
Fig. 3 is the structure diagram of the terminal of a specific embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or has the function of same or like element.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that is used in the specification of the present invention arranges
Diction " comprising " refers to there are the feature, integer, step, operation, element and/or component, but it is not excluded that presence or addition
Other one or more features, integer, step, operation, element, component and/or their group.Wording used herein " and/
Or " include one or more associated list items whole or any cell and all combine.
Those skilled in the art of the present technique are appreciated that unless otherwise defined all terms used herein are (including technology art
Language and scientific terminology), there is the meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless by specific definitions as here, idealization or the meaning of overly formal otherwise will not be used
To explain.
Those skilled in the art of the present technique are appreciated that " terminal " used herein above, " terminal device " both include wireless communication
The equipment of number receiver, only possesses the equipment of the wireless signal receiver of non-emissive ability, and including receiving and transmitting hardware
Equipment, have on bidirectional communication link, can perform two-way communication reception and emit hardware equipment.This equipment
It can include:Honeycomb or other communication equipments, show with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments;PCS (Personal Communications Service, PCS Personal Communications System), can
With combine voice, data processing, fax and/or its communication ability;PDA (Personal Digital Assistant, it is personal
Digital assistants), radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day can be included
It goes through and/or GPS (Global Positioning System, global positioning system) receiver;Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His equipment." terminal " used herein above, " terminal device " they can be portable, can transport, mounted on the vehicles (aviation,
Sea-freight and/or land) in or be suitable for and/or be configured to, in local runtime and/or with distribution form, operate in the earth
And/or any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or with music/video playing function mobile phone or the equipment such as smart television, set-top box.
As shown in Figure 1, to extract the flow diagram of the method for big beat information in the slave music beat point of an embodiment,
The method comprising the steps of:
S110, each beat point according to the music of input, obtain several candidates beat cycle.
The music that music can be the music in music libraries or user oneself uploads.Since present invention needs carry
Big beat information is taken out, so the music of input needs the playing information with big beat.Exemplified by Israeli troops drum, in the music of input
Need the information played with army's drum.Music beat point is that frame drum percussion in music, piano stress, voice climax etc. possess
The general designation at the time point of stronger rhythmic appearance.Beat is the unit for weighing rhythm, in music, there is the one of certain strong and weak difference
Serial bat repeats at regular intervals.If one group of event or phenomenon are repeated by same order, completion
The time or space interval of this group of event or phenomenon are known as the cycle.
Several candidates beat cycle is calculated for subsequent analysis firstly the need of from all beat points, wherein, from
Each beat point is obtained in music data to be realized according to existing mode in the prior art (at this time without classification).
S120, several beat point sequences in generation each candidate's beat cycle, and calculate the power of each beat point sequence
Weight, wherein, two neighboring beat point is using corresponding candidate's beat cycle as interval in the beat point sequence.
For each candidate's beat cycle, several beat point sequences are generated.Each beat point sequence includes each
A beat point, two neighboring beat point is using corresponding candidate's beat cycle as interval.Beat point according to the time sequencing according to
Secondary arrangement, two neighboring beat point refer to front and rear two beat points being close to.Two neighboring beat point is saved with corresponding candidate
The cycle is clapped to be spaced the positive integer times at intervals of corresponding candidate's beat cycle for referring to two neighboring beat point, and allows to have
Certain error, such as ± 5% error.
For example, candidate's beat cycle is T, which corresponds to 2 beat point sequences.One of section
Clapping point sequence includes { beat point 1, beat point 2, beat point 3 }, and beat point 1 and beat point 2 are two neighboring beat point, the two it
Between at intervals of 97%T, beat point 2 and beat point 3 are two neighboring beat point, between the two at intervals of 102%T.It is another
A beat point sequence includes { beat point 4, beat point 5, beat point 6 }, and beat point 4 and beat point 5 are two neighboring beat point, and two
Between person at intervals of 97%2T, beat point 5 and beat point 6 are two neighboring beat point, between the two at intervals of 102%
3T。
For each candidate's beat cycle, several corresponding beat point sequences of candidate beat cycle are obtained, and are counted
Calculate the weight of each beat point sequence.The weight of beat point sequence refers to that the beat point sequence is relatively heavy in the overall evaluation
Want degree.
S130, from several beat point sequences in each candidate's beat cycle weight selection maximum beat point sequence,
Maximum weights sequence as each candidate's beat cycle.
For each candidate's beat cycle, which includes each beat point sequence, each section
Clapping point sequence, there are one weights, then the beat point sequence of weight selection maximum, the beat point sequence are candidate's beat week
The maximum weights sequence of phase, and so on, you can to obtain the maximum weights sequence in each candidate's beat cycle.It is appreciated that
When candidate's beat cycle is only there are one during beat point sequence, which is the most authority in candidate's beat cycle
Value sequence.
S140, according to the maximum weights sequence in each candidate's beat cycle and corresponding weight, obtain big beat information.
Optionally, the big beat information includes big beat cycle and big beat point.The big beat cycle is in music notation
The note total length of each trifle.In music, the time is divided into impartial base unit, and each unit is called one " bat "
Or " one claps ", and several bats form trifle, and what the corresponding reality time was usually fixed, it is referred to as big beat week
Phase.Wherein, the long short reaction of its duration of trifle design of the music score producer to music rhythm speed.Big beat point is pleasure
Bent producer is for one group of periodic beat point that music is allowed to have better sense of auditory rhythm and is added, for there is frame drum
The music played is participated in, rouses to play this group of beat point usually using the army in frame drum, therefore is otherwise known as " army's drumbeat ".
After maximum weights sequence and corresponding weight that each candidate's beat cycle is obtained according to above-mentioned steps, just
According to certain computation rule music corresponding big beat cycle and big beat point etc. can be calculated from music beat point greatly
Beat information.
The present embodiment obtains several candidates beat cycle according to each beat point of input, then obtains each candidate's section
The maximum weights sequence in cycle is clapped, big beat information can be got according to maximum weights sequence and corresponding weight automatically,
It is achieved thereby that the extraction of big beat information.
In one embodiment, each beat point of the music according to input, obtains several candidates beat cycle,
Including:
Time interval in all beat points that S1101, record input between every two neighboring beat point.
The time interval of all beat points of input between any two is recorded.Beat point is included with the beat point of input
1st, exemplified by beat point 2, beat point 3, beat point 4, beat point 5 ..., this step is recorded between beat point 1 and beat point 2
Time interval, the time interval between beat point 2 and beat point 3, the time interval between beat point 3 and beat point 4, beat point
Time interval between 4 and beat point 5, and so on.Optionally, the latter beat in time interval, that is, two neighboring beat point
The time of point subtracts the time of previous beat point.
S1102, the statistics with histogram that Gaussian Profile is carried out to each time interval, obtain histogram, wherein, the Nogata
For the abscissa of figure for characterizing time interval, ordinate is used to characterize the number of time interval appearance.
The statistics with histogram of Gaussian Profile is carried out to each time interval calculated in step S1101.At one
In embodiment, the statistics with histogram that Gaussian Profile is carried out to each time interval, including:
S1102a, structure initial histogram.
A two-dimensional histogram table is established, abscissa represents all possible time interval, and ordinate represents the time
The number occurred is spaced, all numerical value are 0 in table when initial.
S1102b, a time interval is chosen from all time intervals as current time interval.
Optionally, a time interval can be chosen successively according to vertical order as current time interval.
S1102c, the numerical value of current time interval position described in the initial histogram increases to N, and by institute
State in initial histogram and own | t-T | the numerical value at the position of < δ increasesWherein, T works as to be described
Preceding time interval, t are the time interval in addition to the current time interval, and δ is predetermined threshold value, and e is natural logrithm function
The truth of a matter.
S1102d, another time interval is chosen from all time intervals as current time interval, returned by described in
The numerical value of current time interval position described in initial histogram increases N, and will own in the initial histogram | t-
T | the numerical value at the position of < δ increases The step of, it is taken as until all time intervals are selected
For current time interval.
The precision for ensureing statistical result while error influences is eliminated using the statistics with histogram mode of Gaussian Profile.
S1103, peak detection is carried out to the histogram, obtains several peak points.
Peak detection is carried out to histogram according to setting inspection peak condition, obtains each peak point.In one embodiment, examine
The minimum value of data of the peak condition between the continuous peak of any two should be lower than the half at the two peaks.It should be appreciated that this
Invention is not restricted to detect peak point by above-mentioned inspection peak condition, and user can also use other inspection peak conditions.
S1104, the peak point that the order of number from big to small chooses preset number is corresponded to according to peak point, by preset number
Peak point corresponding to interval time as candidate's beat cycle.
To all peak points calculated in step S1103, it is maximum (i.e. number is maximum) to choose wherein histogram values
M peak corresponding to interval time exported as candidate's beat cycle.
For each candidate's beat cycle, the most authority using the cycle as interval is extracted from all beat points
The periodic sequences such as value, that is to say maximum weights sequence.Here it is proper equal that " waiting the cycles ", which is not, but is allowed
There are certain error, such as ± 5% error, meanwhile, also allow there are a degree of leak source, i.e., when two neighboring in sequence
When the interval of point meets the positive integer times for the cycle, also it is regarded as equally spaced.
The maximum weights sequence of extraction needs first to obtain several beat point sequences in each candidate's beat cycle, then could
Therefrom select maximum weights sequence.In one embodiment, several beat points in generation each candidate's beat cycle
Sequence, including:
S1201, candidate's beat cycle is chosen from all candidate's beat cycles as the current beat cycle.
The optional candidate beat cycle is as the current beat cycle.
S1202, a beat point is chosen from all beat points of input as starting beat point.
A starting beat point of the optional beat point as the current beat cycle.When selection originates beat point, it is
Facilitate reading, optionally, each beat point can be selected successively according to vertical order as starting beat point.
S1203, the interval found from the beat point behind the starting beat point between the starting beat point are expired
The beat point of sufficient isoperimetric phase spaced apart condition, wherein, the isoperimetric phase spaced apart condition includes the interval and current beat cycle
Error between positive integer times is in setting range.
Each beat point of input is arranged in order according to the sequencing of time.To originate beat point as starting point, from going to
The beat point for meeting isoperimetric phase spaced apart condition is begun look for afterwards, if it is found, corresponding beat point is recorded.During isoperimetric
Parting bead part includes the error being spaced between the positive integer times in current beat cycle in setting range, and that is to say allows to have
Certain error, meanwhile, also allow there are a degree of leak source, i.e., when the interval of two points meets the positive integer times for the cycle
When, it is also regarded as equally spaced.
In the specific implementation, the cycles such as first satisfaction can be begun look for from front to back to originate beat point as starting point
The beat point of spaced apart condition, if it is found, the beat point is recorded.The beat point that upper one is found is set to new and rises
Point, repeats the above process, until obtaining all beat points using the starting beat point as starting point.
S1204, one that the current beat cycle is made of the starting beat point and all beat points searched out
Beat point sequence.
Starting beat point and all beat points found form a beat point sequence in current beat cycle.
S1205, another beat point is chosen from all beat points of input as starting beat point, returned from described
The beat that the interval between the starting beat point meets isoperimetric phase spaced apart condition is found in beat point behind beginning beat point
The step of point, until all beat points are selected as starting beat point, obtains all beats in the current beat cycle
Point sequence.
The beat point of a not processed mistake is chosen as new starting beat point, optionally, chooses the starting beat
Next beat point of point is as new starting beat point, and then repeatedly step S1202 and step S1203, obtains current beat
Another beat point sequence in cycle.Starting beat point is updated again, and repeats above-mentioned step, until obtaining working as prosthomere
Clap all beat point sequences in cycle.
S1206, another candidate beat cycle is chosen from all candidate's beat cycles as the current beat cycle, returned
A step of beat point is as starting beat point is chosen from all beat points of input, until all candidate's beat cycles are equal
It is selected as the current beat cycle.
After obtaining all beat point sequences in a current beat cycle, another not processed candidate's beat is chosen
Cycle, as the new current beat cycle, all beat point sequences in new current beat cycle were obtained by above-mentioned steps.Again
The current beat cycle is updated, and repeats above-mentioned step, until all candidate's beat cycles are selected processing.Extremely
This, just obtains respective corresponding all beat point sequences of all candidate's beat cycles.
It obtains after all beat point sequences, it is necessary to weight be asked for beat point sequence, for comparing with each beat
The weight for the beat point sequence that point is obtained as starting point, selects weight of the maximum weight as candidate's beat cycle,
Maximum weights sequence of the beat point sequence as candidate's beat cycle corresponding to it.
The requirement of weight calculation design is that the beat cycle greatly to be allowed really to obtain higher weight, while some are easily produced
The cycle value of raw interference obtains lower weight.Conventional music beat is clapped for 2/4,3/4 claps, 4/4 claps, therefore institute of the present invention
It states schema definition and easily generates the numerical value of interference and be:1/2 big beat cycle, 1/3 big beat cycle, 2 times big beat cycle determine
The reason for adopted, is based on some following:
1. for 2/4 bat and 4/4 music clapped, there may be a beat point at the 1/2 of each trifle, so as to lead
Cause the interference in 1/2 big beat cycle.
2. for the music that 3/4 claps, there may be beat point at the 1/3 of each trifle and 2/3, so as to cause 1/
The interference in 3 big beat cycles.
3. for the music of any beat, it is possible in such as 3/8 trifle, 5/16 trifle etc. there are beat point,
But the presence that typically, such beat point will not be steady in a long-term, thus the interference caused by it can be ignored.
4. when music switches between strong rhythm and weak rhythm, it is possible to can deliberately dispense some big beat points, together
When to preselect the accuracy of beat detection be not 100%, it is possible to can missing inspection some big beat points, it is all so as to cause 2 times big beat
Phase is disturbed.
Preferably to distinguish real big beat and interference, the present invention claims beat point detection algorithm to all beat points
Intensity division is carried out, is divided into strong beat point and weak beat point, i.e., described beat point includes strong beat point and weak beat point.
Weak for the last one one when clapping cycle by two units in the cycling of beat, the last one two is weak at three, and only there are one carried during forte
Strong beat is named in the unit bat of forte, and weak beat is without the unit bat of forte.Based on the fact that:It is to highlight melody during music playing
Rhythm is often played at big beat point using higher intensity, therefore is detected as strong beat point than being detected as weak section
It is more likely big beat point to clap point.
Based on the above points, in one embodiment, the weight for calculating each beat point sequence, including:
S1207, a beat point sequence is chosen from all beat point sequences as current beat point sequence.
S1208, two adjacent beat points in the current beat point sequence are sequentially obtained.
If two adjacent beat points are strong beat point in S1209, the current beat point sequence, work as prosthomere by described in
The weight for clapping point sequence adds the first setting value.
In a beat point sequence, if continuous two when beat point is strong at equal intervals, by the beat point sequence
Weight adds the first setting value.First setting value can be determined according to actual needs, such as the first setting value is arranged to 7.
If in S1210, the current beat point sequence in two adjacent beat points one for strong beat point another be
Weak beat point, by the weight of the current beat point sequence plus the second setting value, wherein, second setting value is less than described
First setting value.
In a beat point sequence, if continuous two at equal intervals beat point for the last one one it is weak when, by the beat point sequence
The weight of row adds the second setting value.Second setting value can be determined according to actual needs, such as the second setting value is set
For 3.
If two adjacent beat points are weak beat point in S1211, the current beat point sequence, work as prosthomere by described in
The weight of point sequence is clapped plus the 3rd setting value, wherein, the 3rd setting value is less than second setting value.
In a beat point sequence, if continuous two when beat point is weak at equal intervals, by the beat point sequence
Weight adds the 3rd setting value.3rd setting value can be determined according to actual needs, such as the 3rd setting value is arranged to 1.
If the interval of two adjacent beat points is more than corresponding candidate's beat in S1212, the current beat point sequence
The weight of the current beat point sequence is reduced the 4th setting value by the cycle.
In a beat point sequence, if the interval of continuous two beats point is more than candidate's beat cycle, power
It reduces again.Optionally, the 4th setting value is 2 (t-1)2, wherein t is the periodicity at interval.It should be appreciated that the 4th of the present invention the sets
Definite value is not restricted to above-mentioned method of determination.
S1213, the weight that the adjacent beat point of each two obtains in time current beat point sequence will be gone through, with corresponding time
The evolution in beat cycle is selected to be multiplied, obtains the final weight of the current beat point sequence.
By above-mentioned steps be calculated the weight of beat point sequence will also multiplied by with the evolution of candidate's beat cycle value,
Just obtain the final weight of beat point sequence.
S1214, another beat point sequence is chosen from all beat point sequences as current beat point sequence, return according to
Sequence obtains the step of two adjacent beat points in the current beat point sequence, until all beat point sequences are selected
As current beat point sequence.
It should be appreciated that the present invention is not restricted to the mode of above-mentioned calculating weight, user can also carry out above-mentioned steps
The deletion or addition of simple deformation and/or step, without departing from being detected as strong beat point than being detected as weak beat point
It is more likely the technical concept of big beat point, within protection scope of the present invention.
In order to be better understood from the calculation of above-mentioned weight, illustrated with reference to an example.
Assuming that a beat point sequence is { beat point 1, beat point 2, beat point 3, beat point 4 }, wherein, beat point 1 is
Strong beat point, beat point 2 are strong beat point, and beat point 3 is weak beat point, and beat point 4 is weak beat point, and, beat point 1 and section
Clap between point 2 at intervals of 3T, T is beat point sequence corresponding candidate's beat cycle.The weight of so beat point sequence is:
(7+3+1-8)*T1/2=3T1/2。
In one embodiment, the maximum weights sequence in the basis each candidate's beat cycle and corresponding weight,
Big beat information is obtained, including:It S1401, candidate's beat cycle that weight maximum is selected from all candidate's beat cycles, will select
The candidate's beat cycle selected, as the big beat cycle, each in the maximum weights sequence in candidate's beat cycle of selection was saved
It claps point and is used as big beat point.That candidate's beat cycle of weight maximum in all candidate's beat cycles was exported as big beat week
Phase, each beat point in big beat cycle corresponding maximum weights sequence is big beat point.
It should be appreciated that the present invention is not restricted to the above-mentioned mode for determining big beat information, in the range of error permission,
Candidate's beat cycle that weight is time big can also be selected from all candidate's beat cycles, using the candidate's beat cycle selected as
The big beat cycle, using each beat point in the maximum weights sequence in the candidate's beat cycle selected as big beat point.
Due to the introducing of weight, when the interval between continuous two beats point is more than 1 cycle, weight can reduce, because
This is likely to occur the beats interval such as satisfaction between some beat points and selected big beat point, but is not belonging to big beat cycle correspondence
Maximum weights sequence.And in the case where meeting certain condition, these beat points should also be as being judged as big beat point, therefore
Maximum weights sequence corresponding to the big beat cycle is needed to carry out addendum operation, that is, supplements the big beat point of omission.
In one embodiment, described each beat point by the maximum weights sequence in candidate's beat cycle of selection
After big beat point, further include:If other beats in S1402, all beat points inputted in addition to as big beat point
In point, there are the positive integer times at intervals of the big beat cycle between beat point and any one big beat point, and the interval
The beat point is determined as big beat point by the big beat cycle no more than 2 times.
In the present embodiment, if between some non-big beat point and any one big beat point at intervals of the big beat cycle
Positive integer times, and the interval between the non-big beat point and any big beat point is no more than the 2 times big beat cycle, then it is this is non-big
Beat point is determined as big beat point.Any one big beat point refers to arbitrary in corresponding maximum weights sequence of big beat cycle
The one big beat point chosen.At intervals of the positive integer times in big beat cycle, certain error range is also allowed for, i.e. interval
It will be near the integral multiple in big beat cycle.
In another embodiment, described each beat by the maximum weights sequence in candidate's beat cycle of selection
Point is further included as after big beat point:
If in other beat points in S1403, all beat points inputted in addition to as big beat point, there are two beats
Point any one big beat point between interval be the big beat cycle positive integer times, and between two beat points between
The big beat cycle is divided into, which is determined as big beat point.
It it is the big beat cycle when there are two, non-big beat point is satisfied by with the interval between any one big beat point
Positive integer times, and between the two non-big beat points at intervals of 1 big beat cycle when the two non-big beat points are equal
It is determined as big beat point.
The big beat information obtained can be applied to various scenes.It is introduced with reference to two examples.It should be appreciated that
The big beat information that the present invention obtains is not restricted to be applied to following two kinds of scenes, and user can also be as needed by big beat
Information application is into other scenes.
For example, add default rhythm special efficacy on the big beat point of the big beat information instruction.Rhythm special efficacy
Refer to the special efficacy related with rhythm, such as light efficiency special efficacy, burst point special efficacy etc..Big beat information can be fed directly to video
FX Module, when user carries out video record, by adding specific rhythm special efficacy on these big beat points so that
Entire video effect can match with music rhythm.
In another example the beat point testing result of the music is modified and to residue according to the big beat information
Beat point carries out classification classification, then adds default emotion type special efficacy on remaining beat point.Emotion type special efficacy refer to
The related special efficacy of emotion, such as:It represents the special efficacy of happiness, represents special efficacy saved worry etc..The big beat information calculated can be with
Sending back to beat detection program aids in it to be modified beat point testing result, to improve accuracy, wherein, according to big beat
The mode that big beat cycle in information etc. is modified beat point testing result can be according to existing side in the prior art
Formula is realized.It can also carry out classification classification to remaining beat point according to big beat information, such as by the section in addition to big beat point
Clap point and be classified as one kind, the grade of such intensity less than the intensity of big beat point grade, so as to by different classes of varying strength
Beat point be applied to different scenes.In addition, equally remaining beat point information can be fed directly to special video effect module, when
When user carries out video record, by adding specific emotion special efficacy on remaining beat point, the accurate of special video effect is promoted
Degree and the degrees of coordination with music.
As shown in Fig. 2, the schematic diagram of the big beat information application scenarios for a specific embodiment.When user has selected music
Music in storehouse or when oneself uploading a piece of music, products application program will calculate one group of pre-selection according to music audio data
Beat point information, scheme of the present invention will then be called to calculate the corresponding big beat letter of music from pre-selection beat point
Breath, i.e., big beat cycle and big beat point.
On the one hand the big beat information calculated will send back to beat detection program and it is aided in carry out beat testing result
It corrects to improve accuracy and carry out classification classification to remaining beat point, remaining beat point is then fed directly to video spy
Module is imitated, when user carries out video record, by adding specific emotion type special efficacy in these remaining beat points, so as to
Further promote the accuracy of the special video effect of addition and the degrees of coordination with music.
On the other hand the big beat information calculated will be fed directly to special video effect module, when user carries out video record
When, by adding specific rhythm special efficacy in these big beat points, final video output effect is enabled to preferably to paste
The rhythm of synaeresis pleasure, so as to reach better viewing experience.
The embodiment of the present invention additionally provides a kind of computer readable storage medium, is stored thereon with computer program, the journey
The method that big beat information is extracted in the slave music beat point described in foregoing any one is realized when sequence is executed by processor.It is described
Storage medium includes but not limited to any kind of disk (including floppy disk, hard disk, CD, CD-ROM and magneto-optic disk), ROM
(Read-Only Memory, read-only memory), RAM (Random AcceSS Memory, immediately memory), EPROM
(EraSable Programmable Read-Only Memory, Erarable Programmable Read only Memory), EEPROM
(Electrically EraSable Programmable Read-Only Memory, Electrically Erasable Programmable Read-Only Memory),
Flash memory, magnetic card or light card.It is, storage medium includes by equipment (for example, computer) so as to the form read
Any medium of storage or transmission information.Can be read-only memory, disk or CD etc..
The embodiment of the present invention additionally provides a kind of terminal, and the terminal includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes the method that big beat information is extracted in the slave music beat point described in foregoing any one.
As shown in figure 3, it for convenience of description, illustrates only and the relevant part of the embodiment of the present invention, particular technique details
It does not disclose, refer to present invention method part.The terminal can be to include mobile phone, tablet computer, PDA
(Personal Digital Assistant, personal digital assistant), POS (Point of Sales, point-of-sale terminal), vehicle mounted electric
The arbitrary terminal device such as brain, by terminal for exemplified by mobile phone:
Fig. 3 is illustrated that the block diagram with the part-structure of the relevant mobile phone of terminal provided in an embodiment of the present invention.Reference chart
3, mobile phone includes:Radio frequency (Radio Frequency, RF) circuit 1510, memory 1520, input unit 1530, display unit
1540th, sensor 1550, voicefrequency circuit 1560, Wireless Fidelity (wireless fidelity, Wi-Fi) module 1570, processor
The components such as 1580 and power supply 1590.It will be understood by those skilled in the art that the handset structure shown in Fig. 3 is not formed pair
The restriction of mobile phone can include either combining some components or different component cloth than illustrating more or fewer components
It puts.
Each component parts of mobile phone is specifically introduced with reference to Fig. 3:
RF circuits 1510 can be used for receive and send messages or communication process in, signal sends and receivees, particularly, by base station
After downlink information receives, handled to processor 1580;In addition, the data sending of uplink will be designed to base station.In general, RF circuits
1510 include but not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier (Low Noise
Amplifier, LNA), duplexer etc..In addition, RF circuits 1510 can also be led to by wireless communication and network and other equipment
Letter.Above-mentioned wireless communication can use any communication standard or agreement, include but not limited to global system for mobile communications (Global
System of Mobile communication, GSM), general packet radio service (General Packet Radio
Service, GPRS), CDMA (Code Division Multiple Access, CDMA), wideband code division multiple access
(Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution,
LTE), Email, Short Message Service (Short Messaging Service, SMS) etc..
Memory 1520 can be used for storage software program and module, and processor 1580 is stored in memory by operation
1520 software program and module, so as to perform the various function application of mobile phone and data processing.Memory 1520 can be led
To include storing program area and storage data field, wherein, storing program area can storage program area, needed at least one function
Application program (such as big beat information abstraction function etc.) etc.;Storage data field can be stored uses created number according to mobile phone
According to (such as big beat information etc.) etc..In addition, memory 1520 can include high-speed random access memory, can also include non-
Volatile memory, for example, at least a disk memory, flush memory device or other volatile solid-state parts.
Input unit 1530 can be used for the number for receiving input or character information and generate with the user setting of mobile phone with
And the key signals input that function control is related.Specifically, input unit 1530 may include touch panel 1531 and other inputs
Equipment 1532.Touch panel 1531, also referred to as touch-screen collect user on it or neighbouring touch operation (such as user
Use the behaviour of any suitable object such as finger, stylus or attachment on touch panel 1531 or near touch panel 1531
Make), and corresponding attachment device is driven according to preset formula.Optionally, touch panel 1531 may include touch detection
Two parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation band
The signal come, transmits a signal to touch controller;Touch controller receives touch information from touch detecting apparatus, and by it
Contact coordinate is converted into, then gives processor 1580, and the order that processor 1580 is sent can be received and performed.In addition,
The polytypes such as resistance-type, condenser type, infrared ray and surface acoustic wave may be employed and realize touch panel 1531.Except touch surface
Plate 1531, input unit 1530 can also include other input equipments 1532.Specifically, other input equipments 1532 can include
But it is not limited in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operation lever etc.
It is one or more.
Display unit 1540 is each available for the information and mobile phone for showing by information input by user or being supplied to user
Kind menu.Display unit 1540 may include display panel 1541, optionally, liquid crystal display (Liquid may be employed
Crystal Display, LCD), the forms such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED)
To configure display panel 1541.Further, touch panel 1531 can cover display panel 1541, when touch panel 1531 detects
To processor 1580 on it or after neighbouring touch operation, is sent to determine the type of touch event, device is followed by subsequent processing
1580 provide corresponding visual output according to the type of touch event on display panel 1541.Although in figure 3, touch panel
1531 and display panel 1541 are the components independent as two to realize the input of mobile phone and input function, but in some realities
Apply in example, can be integrated by touch panel 1531 and display panel 1541 and that realizes mobile phone output and input function.
Mobile phone may also include at least one sensor 1550, such as optical sensor, motion sensor and other sensors.
Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein, ambient light sensor can be according to ambient light
Light and shade adjust the brightness of display panel 1541, proximity sensor can close display panel when mobile phone is moved in one's ear
1541 and/or backlight.As one kind of motion sensor, accelerometer sensor can detect in all directions (generally three axis) and add
The size of speed can detect that size and the direction of gravity when static, application (such as the horizontal/vertical screen available for identification mobile phone posture
Switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.;As for mobile phone also
The other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared ray sensor, details are not described herein.
Voicefrequency circuit 1560, loud speaker 1561, microphone 1562 can provide the audio interface between user and mobile phone.Audio
The transformed electric signal of the voice data received can be transferred to loud speaker 1561, is converted by loud speaker 1561 by circuit 1560
For vocal print signal output;On the other hand, the vocal print signal of collection is converted to electric signal by microphone 1562, by voicefrequency circuit 1560
Voice data is converted to after reception, then after voice data output processor 1580 is handled, through RF circuits 1510 to be sent to ratio
Voice data is exported to memory 1520 to be further processed by such as another mobile phone.
Wi-Fi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronics by Wi-Fi module 1570
Mail, browsing webpage and access streaming video etc., it has provided wireless broadband internet to the user and has accessed.Although Fig. 3 is shown
Wi-Fi module 1570, but it is understood that, and must be configured into for mobile phone is not belonging to, completely it can exist as needed
Do not change in the scope of the essence of invention and omit.
Processor 1580 is the control centre of mobile phone, using various interfaces and the various pieces of connection whole mobile phone,
Memory 1520 is stored in by running or performing the software program being stored in memory 1520 and/or module and call
Interior data perform the various functions of mobile phone and processing data, so as to carry out integral monitoring to mobile phone.Optionally, processor
1580 may include one or more processing units;Preferably, processor 1580 can integrate application processor and modulation /demodulation processing
Device, wherein, the main processing operation system of application processor, user interface and application program etc., modem processor is mainly located
Manage wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 1580.
Mobile phone is further included to the power supply 1590 (such as battery) of all parts power supply, it is preferred that power supply can pass through power supply
Management system and processor 1580 are logically contiguous, so as to realize management charging, electric discharge and power consumption pipe by power-supply management system
The functions such as reason.
Although being not shown, mobile phone can also include camera, bluetooth module etc., and details are not described herein.
Method, storage medium and the terminal of big beat information are extracted in above-mentioned slave music beat point, with prior art phase
When mutually relatively, possesses advantages below:
1st, several candidates beat cycle is obtained according to each beat point of input, then obtains each candidate's beat cycle
Maximum weights sequence, big beat information can be got according to maximum weights sequence and corresponding weight automatically, so as to real
The extraction of big beat information is showed.
2nd, it is further, on the one hand, a subseries has been carried out to music beat point, wherein will can most represent music rhythm
Big beat point individually is extracted out, by adding specific rhythm special efficacy on these big beat points, enables to final
Video output effect is preferably bonded the rhythm of music, so as to reach better viewing experience;On the other hand, believe with reference to big beat
Breath can preferably be modified remaining beat point classifies with analysis, and it is special that emotion type is then added on remaining beat point
Effect, the degrees of coordination so as to the accuracy for further promoting the special video effect of addition and with music.
3rd, it is further, statistics with histogram is carried out using the mode of Gaussian Profile, is ensured while eliminating error and influencing
The precision of statistical result, so as to obtain more accurate big beat information.
4th, it is further, the weight of each beat point sequence is calculated by the weight calculation mode of design, so as to
Common 1/2, the interference in 1/3,2 times big beat cycle are effectively reduced, obtains correct big beat information.
5th, big beat point that is further, being omitted by decision condition supplement further improves big beat point extraction
Accuracy.
It should be understood that although each step in the flow chart of attached drawing is shown successively according to the instruction of arrow,
These steps are not that the inevitable order according to arrow instruction performs successively.Unless it expressly states otherwise herein, these steps
Execution there is no stringent orders to limit, can perform in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps can include multiple sub-steps, and either these sub-steps of multiple stages or stage are not necessarily in synchronization
Completion is performed, but can be performed at different times, execution sequence is also not necessarily to carry out successively, but can be with other
Either the sub-step of other steps or at least a portion in stage perform step in turn or alternately.
The above is only some embodiments of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
1. the method for big beat information is extracted in a kind of point from music beat, which is characterized in that including step:
According to each beat point of the music of input, several candidates beat cycle is obtained;
Several beat point sequences in each candidate's beat cycle are generated, and calculate the weight of each beat point sequence, wherein, institute
Two neighboring beat point is stated in beat point sequence using corresponding candidate's beat cycle as interval;
The beat point sequence of weight selection maximum from several beat point sequences in each candidate's beat cycle, as each time
Select the maximum weights sequence in beat cycle;
According to the maximum weights sequence in each candidate's beat cycle and corresponding weight, big beat information is obtained.
2. the method for big beat information is extracted in the point according to claim 1 from music beat, which is characterized in that described
According to each beat point of the music of input, several candidates beat cycle is obtained, including:
Record the time interval between every two neighboring beat point in all beat points of input;
The statistics with histogram of Gaussian Profile is carried out to each time interval, obtains histogram, wherein, the abscissa of the histogram
For characterizing time interval, ordinate is used to characterize the number of time interval appearance;
Peak detection is carried out to the histogram, obtains several peak points;
The peak point of the order selection preset number of number from big to small is corresponded to according to peak point, by the peak point institute of preset number
Corresponding interval time is as candidate's beat cycle.
3. the method for big beat information is extracted in the point according to claim 2 from music beat, which is characterized in that described right
Each time interval carries out the statistics with histogram of Gaussian Profile, including:
Build initial histogram;
A time interval is chosen from all time intervals as current time interval;
The numerical value of current time interval position described in the initial histogram is increased into N, and by the initial histogram
Own in figure | t-T |<Position at numerical value increase Wherein, T be the current time interval, t
For the time interval in addition to the current time interval, δ is predetermined threshold value;
Another time interval is chosen from all time intervals as current time interval, returning will be in the initial histogram
The numerical value of the current time interval position increases N, and will own in the initial histogram | t-T |<At the position of δ
Numerical value increaseThe step of, until all time intervals are selected as between current time
Every.
4. the method for big beat information is extracted in the point according to claim 1 from music beat, which is characterized in that the section
Clapping point includes strong beat point and weak beat point;
The weight for calculating each beat point sequence, including:
A beat point sequence is chosen from all beat point sequences as current beat point sequence;
Sequentially obtain two adjacent beat points in the current beat point sequence;
If two adjacent beat points are strong beat point in the current beat point sequence, by the current beat point sequence
Weight adds the first setting value;
If in the current beat point sequence in two adjacent beat points one for strong beat point another be weak beat point, will
The weight of the current beat point sequence adds the second setting value, wherein, second setting value is less than first setting value;
If two adjacent beat points are weak beat point in the current beat point sequence, by the current beat point sequence
Weight adds the 3rd setting value, wherein, the 3rd setting value is less than second setting value;
If the interval of two adjacent beat points is more than corresponding candidate's beat cycle in the current beat point sequence, by described in
The weight of current beat point sequence reduces the 4th setting value;
The weight obtained all over the adjacent beat point of each two in the current beat point sequence will be gone through, with corresponding candidate's beat cycle
Evolution be multiplied, obtain the final weight of the current beat point sequence;
Another beat point sequence is chosen from all beat point sequences as current beat point sequence, is returned described in sequentially obtaining
In current beat point sequence the step of two adjacent beat points, until all beat point sequences are selected as working as prosthomere
Clap point sequence.
5. the method for big beat information, feature are extracted in the point according to any one of claims 1 to 4, from music beat
It is, several beat point sequences in generation each candidate's beat cycle, including:
Candidate's beat cycle is chosen from all candidate's beat cycles as the current beat cycle;
A beat point is chosen from all beat points of input as starting beat point;
It is found from the beat point behind the starting beat point during meeting isoperimetric the interval originated between beat point
The beat point of parting bead part, wherein, the isoperimetric phase spaced apart condition include the interval and the positive integer times in current beat cycle it
Between error in setting range;
A beat point sequence in the current beat cycle is made of the starting beat point and all beat points searched out;
Another beat point is chosen from all beat points of input as starting beat point, is returned after the starting beat point
The step of interval between the starting beat point meets the beat point of isoperimetric phase spaced apart condition is found in the beat point in face, directly
It is selected as starting beat point to all beat points;
Another candidate's beat cycle is chosen from all candidate's beat cycles as the current beat cycle, returns to the institute from input
Have and a step of beat point is as starting beat point is chosen in beat point, until all candidate's beat cycles are selected conduct
The current beat cycle.
6. the method for big beat information, feature are extracted in the point according to any one of claims 1 to 4, from music beat
It is, the big beat information includes big beat cycle and big beat point;
The maximum weights sequence and corresponding weight in basis each candidate's beat cycle, obtain big beat information, including:
Candidate's beat cycle of weight maximum is selected from all candidate's beat cycles, using the candidate's beat cycle selected as big
The beat cycle, using each beat point in the maximum weights sequence in the candidate's beat cycle selected as big beat point.
7. the method for big beat information is extracted in the point according to claim 6 from music beat, which is characterized in that described to incite somebody to action
After each beat point in the maximum weights sequence in the candidate's beat cycle selected is as big beat point, further include:
It is if big with any one there are beat point in other beat points in all beat points of input in addition to as big beat point
The positive integer times at intervals of the big beat cycle between beat point, and the big beat cycle of the interval no more than 2 times, this is saved
It claps point and is determined as big beat point.
8. the method for big beat information is extracted in the point according to claim 6 from music beat, which is characterized in that described to incite somebody to action
After each beat point in the maximum weights sequence in the candidate's beat cycle selected is as big beat point, further include:
If in other beat points in all beat points of input in addition to as big beat point, there are two beat points and any one
Interval between a big beat point is the positive integer times in big beat cycle, and between two beat points at intervals of big beat
Two beat points are determined as big beat point by the cycle.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The method for extracting big beat information from music beat point as claimed in any of claims 1 to 8 in one of claims is realized during row.
10. a kind of terminal, which is characterized in that the terminal includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The method for now extracting big beat information from music beat point as claimed in any of claims 1 to 8 in one of claims.
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711466076.3A CN108108457B (en) | 2017-12-28 | 2017-12-28 | Method, storage medium, and terminal for extracting large tempo information from music tempo points |
RU2020124337A RU2773876C2 (en) | 2017-12-28 | 2018-12-04 | Method for extraction of big-bit information from fractions of musical beat, data carrier and terminal |
EP18894999.4A EP3734468A4 (en) | 2017-12-28 | 2018-12-04 | Method for extracting big beat information from music beat points, storage medium and terminal |
US16/957,935 US11386876B2 (en) | 2017-12-28 | 2018-12-04 | Method for extracting big beat information from music beat points, storage medium and terminal |
PCT/CN2018/119108 WO2019128638A1 (en) | 2017-12-28 | 2018-12-04 | Method for extracting big beat information from music beat points, storage medium and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711466076.3A CN108108457B (en) | 2017-12-28 | 2017-12-28 | Method, storage medium, and terminal for extracting large tempo information from music tempo points |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108108457A true CN108108457A (en) | 2018-06-01 |
CN108108457B CN108108457B (en) | 2020-11-03 |
Family
ID=62214357
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711466076.3A Active CN108108457B (en) | 2017-12-28 | 2017-12-28 | Method, storage medium, and terminal for extracting large tempo information from music tempo points |
Country Status (4)
Country | Link |
---|---|
US (1) | US11386876B2 (en) |
EP (1) | EP3734468A4 (en) |
CN (1) | CN108108457B (en) |
WO (1) | WO2019128638A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109920449A (en) * | 2019-03-18 | 2019-06-21 | 广州市百果园网络科技有限公司 | Beat analysis method, audio-frequency processing method and device, equipment, medium |
WO2019128638A1 (en) * | 2017-12-28 | 2019-07-04 | 广州市百果园信息技术有限公司 | Method for extracting big beat information from music beat points, storage medium and terminal |
CN110688518A (en) * | 2019-10-12 | 2020-01-14 | 广州酷狗计算机科技有限公司 | Rhythm point determining method, device, equipment and storage medium |
CN111128100A (en) * | 2019-12-20 | 2020-05-08 | 网易(杭州)网络有限公司 | Rhythm point detection method and device and electronic equipment |
CN112233662A (en) * | 2019-06-28 | 2021-01-15 | 百度在线网络技术(北京)有限公司 | Audio analysis method and device, computing equipment and storage medium |
CN112289344A (en) * | 2020-10-30 | 2021-01-29 | 腾讯音乐娱乐科技(深圳)有限公司 | Method and device for determining drum point waveform and computer storage medium |
CN112233662B (en) * | 2019-06-28 | 2024-06-07 | 百度在线网络技术(北京)有限公司 | Audio analysis method, device, computing equipment and storage medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6920445B2 (en) * | 2017-08-29 | 2021-08-18 | AlphaTheta株式会社 | Music analysis device and music analysis program |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217729A (en) * | 2013-05-31 | 2014-12-17 | 杜比实验室特许公司 | Audio processing method, audio processing device and training method |
CN102543052B (en) * | 2011-12-13 | 2015-08-05 | 北京百度网讯科技有限公司 | A kind of method and apparatus analyzing music BPM |
US9293124B2 (en) * | 2013-01-22 | 2016-03-22 | Gibson Brands, Inc. | Tempo-adaptive pattern velocity synthesis |
CN105513583A (en) * | 2015-11-25 | 2016-04-20 | 福建星网视易信息系统有限公司 | Display method and system for song rhythm |
CN106652981A (en) * | 2016-12-28 | 2017-05-10 | 广州酷狗计算机科技有限公司 | BPM detection method and device |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5890116A (en) * | 1996-09-13 | 1999-03-30 | Pfu Limited | Conduct-along system |
US7301092B1 (en) * | 2004-04-01 | 2007-11-27 | Pinnacle Systems, Inc. | Method and apparatus for synchronizing audio and video components of multimedia presentations by identifying beats in a music signal |
US20050249080A1 (en) * | 2004-05-07 | 2005-11-10 | Fuji Xerox Co., Ltd. | Method and system for harvesting a media stream |
JP4465626B2 (en) * | 2005-11-08 | 2010-05-19 | ソニー株式会社 | Information processing apparatus and method, and program |
JP4949687B2 (en) | 2006-01-25 | 2012-06-13 | ソニー株式会社 | Beat extraction apparatus and beat extraction method |
US8878041B2 (en) * | 2009-05-27 | 2014-11-04 | Microsoft Corporation | Detecting beat information using a diverse set of correlations |
US20130330062A1 (en) * | 2012-06-08 | 2013-12-12 | Mymusaic Inc. | Automatic creation of movie with images synchronized to music |
CN104620313B (en) | 2012-06-29 | 2017-08-08 | 诺基亚技术有限公司 | Audio signal analysis |
GB2518663A (en) * | 2013-09-27 | 2015-04-01 | Nokia Corp | Audio analysis apparatus |
KR20170106165A (en) * | 2016-03-11 | 2017-09-20 | 삼성전자주식회사 | Method and electronic apparatus for providing music information |
CN107229629B (en) * | 2016-03-24 | 2021-03-19 | 腾讯科技(深圳)有限公司 | Audio recognition method and device |
CN108335687B (en) * | 2017-12-26 | 2020-08-28 | 广州市百果园信息技术有限公司 | Method for detecting beat point of bass drum of audio signal and terminal |
CN108108457B (en) * | 2017-12-28 | 2020-11-03 | 广州市百果园信息技术有限公司 | Method, storage medium, and terminal for extracting large tempo information from music tempo points |
CN108335688B (en) * | 2017-12-28 | 2021-07-06 | 广州市百果园信息技术有限公司 | Method for detecting main beat point in music, computer storage medium and terminal |
-
2017
- 2017-12-28 CN CN201711466076.3A patent/CN108108457B/en active Active
-
2018
- 2018-12-04 EP EP18894999.4A patent/EP3734468A4/en active Pending
- 2018-12-04 US US16/957,935 patent/US11386876B2/en active Active
- 2018-12-04 WO PCT/CN2018/119108 patent/WO2019128638A1/en unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102543052B (en) * | 2011-12-13 | 2015-08-05 | 北京百度网讯科技有限公司 | A kind of method and apparatus analyzing music BPM |
US9293124B2 (en) * | 2013-01-22 | 2016-03-22 | Gibson Brands, Inc. | Tempo-adaptive pattern velocity synthesis |
CN104217729A (en) * | 2013-05-31 | 2014-12-17 | 杜比实验室特许公司 | Audio processing method, audio processing device and training method |
CN105513583A (en) * | 2015-11-25 | 2016-04-20 | 福建星网视易信息系统有限公司 | Display method and system for song rhythm |
CN106652981A (en) * | 2016-12-28 | 2017-05-10 | 广州酷狗计算机科技有限公司 | BPM detection method and device |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019128638A1 (en) * | 2017-12-28 | 2019-07-04 | 广州市百果园信息技术有限公司 | Method for extracting big beat information from music beat points, storage medium and terminal |
US11386876B2 (en) * | 2017-12-28 | 2022-07-12 | Bigo Technology Pte. Ltd. | Method for extracting big beat information from music beat points, storage medium and terminal |
CN109920449A (en) * | 2019-03-18 | 2019-06-21 | 广州市百果园网络科技有限公司 | Beat analysis method, audio-frequency processing method and device, equipment, medium |
CN109920449B (en) * | 2019-03-18 | 2022-03-04 | 广州市百果园网络科技有限公司 | Beat analysis method, audio processing method, device, equipment and medium |
CN112233662A (en) * | 2019-06-28 | 2021-01-15 | 百度在线网络技术(北京)有限公司 | Audio analysis method and device, computing equipment and storage medium |
CN112233662B (en) * | 2019-06-28 | 2024-06-07 | 百度在线网络技术(北京)有限公司 | Audio analysis method, device, computing equipment and storage medium |
CN110688518A (en) * | 2019-10-12 | 2020-01-14 | 广州酷狗计算机科技有限公司 | Rhythm point determining method, device, equipment and storage medium |
CN110688518B (en) * | 2019-10-12 | 2024-05-24 | 广州酷狗计算机科技有限公司 | Determination method, device, equipment and storage medium for rhythm point |
CN111128100A (en) * | 2019-12-20 | 2020-05-08 | 网易(杭州)网络有限公司 | Rhythm point detection method and device and electronic equipment |
CN111128100B (en) * | 2019-12-20 | 2021-04-20 | 网易(杭州)网络有限公司 | Rhythm point detection method and device and electronic equipment |
CN112289344A (en) * | 2020-10-30 | 2021-01-29 | 腾讯音乐娱乐科技(深圳)有限公司 | Method and device for determining drum point waveform and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
RU2020124337A (en) | 2022-01-28 |
US20200335074A1 (en) | 2020-10-22 |
EP3734468A4 (en) | 2020-11-11 |
CN108108457B (en) | 2020-11-03 |
US11386876B2 (en) | 2022-07-12 |
RU2020124337A3 (en) | 2022-01-28 |
EP3734468A1 (en) | 2020-11-04 |
WO2019128638A1 (en) | 2019-07-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108108457A (en) | Method, storage medium and the terminal of big beat information are extracted from music beat point | |
CN108319657B (en) | Method for detecting strong rhythm point, storage medium and terminal | |
CN109819179A (en) | A kind of video clipping method and device | |
CN107948748B (en) | Method, device, mobile terminal and computer storage medium for recommending videos | |
CN109379641A (en) | A kind of method for generating captions and device | |
CN106210755B (en) | A kind of methods, devices and systems playing live video | |
US11545170B2 (en) | Acoustic neural network scene detection | |
CN105979312B (en) | Information sharing method and device | |
CN108156508B (en) | Barrage information processing method and device, mobile terminal, server and system | |
CN108255954A (en) | Using search method, device, storage medium and terminal | |
CN106210266B (en) | A kind of acoustic signal processing method and audio signal processor | |
CN108335687A (en) | The detection method and terminal of audio signal pucking beat point | |
CN110163045A (en) | A kind of recognition methods of gesture motion, device and equipment | |
CN109189300A (en) | A kind of view circularly exhibiting method and apparatus | |
CN108399232A (en) | A kind of information-pushing method, device and electronic equipment | |
CN108763475B (en) | Recording method, recording device and terminal equipment | |
CN110276010A (en) | A kind of weight model training method and relevant apparatus | |
CN105047185B (en) | A kind of methods, devices and systems obtaining audio accompaniment | |
CN113723159A (en) | Scene recognition model training method, scene recognition method and model training device | |
CN109550248A (en) | Virtual objects location recognition method, device, mobile terminal and storage medium | |
CN104091600A (en) | Song position detection method and device | |
CN106341728A (en) | Product information displaying method, apparatus and system in video | |
CN106407359A (en) | Image playing method and mobile terminal | |
CN109587552A (en) | Video personage sound effect treatment method, device, mobile terminal and storage medium | |
CN111666498B (en) | Friend recommendation method based on interaction information, related device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210622 Address after: 31a, 15 / F, building 30, maple mall, bangrang Road, Brazil, Singapore Patentee after: Baiguoyuan Technology (Singapore) Co.,Ltd. Address before: Building B-1, North District, Wanda Commercial Plaza, Wanbo business district, No. 79, Wanbo 2nd Road, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Patentee before: GUANGZHOU BAIGUOYUAN INFORMATION TECHNOLOGY Co.,Ltd. |